Parameter

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. def *(a: Double): Variable[T]

   

   Definition Classes

   Variable

4. def *(a: Variable[T]): Variable[T]

   

   Definition Classes

   Variable

5. def +(a: Double): Variable[T]

   

   Definition Classes

   Variable

6. def +(a: Variable[T]): Variable[T]

   

   Definition Classes

   Variable

7. def -(a: Double): Variable[T]

   

   Definition Classes

   Variable

8. def -(a: Variable[T]): Variable[T]

   

   Definition Classes

   Variable

9. def /(a: Double): Variable[T]

   

   Definition Classes

   Variable

10. def /(other: Variable[T]): Variable[T]

    

    Definition Classes

    Variable

11. final def ==(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

12. final def asInstanceOf[T0]: T0

    

    Definition Classes

    Any

13. def clone(): AnyRef

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

14. final def eq(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

15. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

16. def expand(sizes: List[Int]): Variable[T]

    

    Expand variable to configured size

    Expand variable to configured size

    sizes

    target variable sizes, dim whose size is -1 will be ignored

    Definition Classes

    Variable

17. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

18. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

19. def getInputShape(): Shape

    

    Definition Classes

    Variable

20. def getOutputShape(): Shape

    

    Definition Classes

    Variable

21. def getWeight(): Tensor[T]

    

22. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

23. def indexSelect(dim: Int, index: Int): Variable[T]

    

    Select an index of the input in the given dim and return the subset part.

    Select an index of the input in the given dim and return the subset part. The batch dimension needs to be unchanged. The selected dim would be remove after this operation. For example, if input is: 1 2 3 4 5 6 Select(1, 1) will give output [2 5] Select(1, -1) will give output [3 6]

    dim

    The dimension to select. 0-based index. Cannot select the batch dimension. -1 means the last dimension of the input.

    index

    The index of the dimension to be selected. 0-based index. -1 means the last dimension of the input.

    Definition Classes

    Variable

24. val initMethod: InitializationMethod

    

    A method used to initialize the Parameter.

    A method used to initialize the Parameter. The default value is RandomUniform(-0.05, 0.05)

25. val initWeight: Tensor[T]

    

    The init value for the Parameter

26. val inputShape: Shape

    

    Shape of this Parameter

27. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

28. val kerasParameter: KerasParameter[T]

    

29. var name: String

    

    Definition Classes

    Variable

30. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

31. final def notify(): Unit

    

    Definition Classes

    AnyRef

32. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

33. def replicate(axis: Int, times: Int): Variable[T]

    

    Definition Classes

    Variable

34. def setWeight(tensor: Tensor[T]): Unit

    

35. def slice(dim: Int, startIndex: Int, length: Int): Variable[T]

    

    Same as Narrow in torch.

    Same as Narrow in torch. Slice the input with the number of dimensions not being reduced. The batch dimension needs to be unchanged. For example, if input is: 1 2 3 4 5 6 slice(1, 1, 2) will give output 2 3 5 6 slice(1, 2, -1) will give output 3 6

    dim

    The dimension to narrow. 0-based index. Cannot narrow the batch dimension. -1 means the last dimension of the input.

    startIndex

    Non-negative integer. The start index on the given dimension. 0-based index.

    length

    The length to be sliced. Default is 1.

    Definition Classes

    Variable

36. def squeeze(dims: Array[Int]): Variable[T]

    

    Definition Classes

    Variable

37. def squeeze(dim: Int): Variable[T]

    

    Delete the singleton dimension(s).

    Delete the singleton dimension(s). The batch dimension needs to be unchanged. For example, if input has size (2, 1, 3, 4, 1): Squeeze(dim = 1) will give output size (2, 3, 4, 1) Squeeze(dims = null) will give output size (2, 3, 4)

    Definition Classes

    Variable

38. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

39. def toString(): String

    

    Definition Classes

    AnyRef → Any

40. val trainable: Boolean

    

    It's true by default, meaning the value would be updated by gradient.

41. def unary_-(): Variable[T]

    

    Definition Classes

    Variable

42. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

43. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

44. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )